A method and system for configuring reserve capacity based on wind power quality

Abstract

The present application relates to the technical field of power operation, and more particularly to a method and system for configuring backup capacity based on wind power quality, comprising: dividing wind power into several wind power quality layers according to the output performance of a wind turbine unit; performing clustering analysis on obtained historical meteorological factors and historical wind power data to determine similar days; determining power generation confidence coefficients of each wind power quality layer according to historical wind power data of the similar days; determining risk degrees of each wind power quality layer being unable to generate power according to the power generation confidence coefficients, to configure backup capacity of each wind power quality layer, and to obtain total backup capacity required to be configured for the similar days. The present application considers the fluctuation of the output of the wind turbine unit, and completes the configuration of backup capacity by dividing quality layers, thereby solving the problem that large-scale new energy fluctuation may lead to insufficient backup and load shedding, and improving operation reliability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power operation, and particularly relates to a backup capacity configuration method and system based on wind power quality. BACKGROUND

[0002] With the development of the power system, power grid operation backup is one of the effective ways to deal with sudden accidents and prediction errors, and is an important technical means to maintain the safe and stable operation of the power grid.

[0003] At present, in the operation of the power market, the non-dispatchable nature of new energy makes it often be treated as a "negative load" in dispatching operation. The backup configuration mode does not consider the backup shortage problem caused by new energy fluctuations. In the new power system environment, if the fluctuations and prediction deviations of large-scale new energy output are not considered, it may lead to insufficient backup capacity in the power system, resulting in load shedding, which cannot guarantee the operation reliability and endanger the safety of the power system. Therefore, there is an urgent need for a backup capacity configuration method that takes into account the fluctuations of new energy. SUMMARY

[0004] The present application provides a backup capacity configuration method and system based on wind power quality, which solves the technical problem that the traditional backup capacity configuration method ignores the backup shortage caused by large-scale new energy fluctuations.

[0005] To solve the above technical problems, the present application provides a backup capacity configuration method and system based on wind power quality.

[0006] In a first aspect, the present application provides a backup capacity configuration method based on wind power quality, which comprises the following steps:

[0007] According to the output performance of the wind turbine unit, the wind power is divided into several wind power quality layers;

[0008] The obtained historical meteorological factors and historical wind power data are subjected to cluster analysis to determine similar days;

[0009] According to the historical wind power data of the similar days, the power generation confidence coefficients of each wind power quality layer are determined;

[0010] According to the power generation confidence coefficients, the risk degrees of the inability of each wind power quality layer to generate power are determined;

[0011] Using the risk degrees, the backup capacity of each wind power quality layer is configured, and the total backup capacity required for the similar days is obtained.

[0012] In a further embodiment, the step of performing clustering analysis on the obtained historical meteorological factors and historical wind power generation data to determine similar days comprises:

[0013] performing linear normalization processing on the obtained historical meteorological factors and historical wind power generation data to obtain normalized meteorological factors and normalized wind power generation data; the historical meteorological factors include historical temperature factors, historical wind speed factors, and historical humidity factors;

[0014] calculating a similarity index and a discrimination index according to the normalized meteorological factors and the normalized wind power generation data;

[0015] performing clustering division on the normalized meteorological factors and the normalized wind power generation data based on the similarity index and the discrimination index to determine similar days.

[0016] In a further embodiment, the calculation formula of the similarity index is:

[0017]

[0018] In the formula, S represents the similarity index; m represents the sample dimension; n represents the total number of historical dates; x ij represents the i-th day, the j-th sample attribute, and the sample attribute includes the normalized meteorological factor or the normalized wind power generation data; represents the average value of the j-th sample attribute;

[0019] The calculation formula of the discrimination index is:

[0020]

[0021] In the formula, D represents the discrimination index; p represents the total number of date categories; P represents the date category number; x iP represents the average value of the j-th sample attribute in the P-th category.

[0022] In a further embodiment, the step of determining the power generation confidence coefficients of each wind power generation quality layer according to the historical wind power generation data of the similar days comprises:

[0023] determining a probability distribution function of wind power generation in a power interval according to the historical wind power generation data of each preset time period of the similar days;

[0024] determining the power generation confidence coefficients of each wind power generation quality layer according to the probability distribution function.

[0025] In a further embodiment, the standby capacity calculation formula of each wind power generation quality layer is:

[0026] P′ k =(P k-P k-1 )*β k

[0027] In the formula, P′ k represents the backup capacity of the kth wind power quality layer; P k represents the upper limit of the unit output of the kth wind power quality layer; P k-1 represents the upper limit of the unit output of the (k-1)th wind power quality layer; β k represents the risk degree of the kth wind power quality layer being unable to generate power.

[0028] In further embodiments, the total backup capacity required for the similar day is obtained, specifically:

[0029]

[0030] In the formula, P total represents the total backup capacity required for the similar day; P′ k represents the backup capacity of the kth wind power quality layer; and K represents the total number of wind power quality layers.

[0031] In further embodiments, the output performance of the wind turbine unit includes the fluctuation of wind power.

[0032] In a second aspect, the present application provides a backup capacity configuration system based on wind power quality, which comprises:

[0033] a quality division module, configured to divide wind power into a plurality of wind power quality layers according to the output performance of the wind turbine unit;

[0034] a clustering analysis module, configured to perform clustering analysis on the obtained historical meteorological factors and historical wind power data to determine similar days;

[0035] a confidence coefficient determination module, configured to determine the power generation confidence coefficients of each wind power quality layer according to the historical wind power data of the similar days;

[0036] a risk degree determination module, configured to determine the risk degrees of each wind power quality layer being unable to generate power according to the power generation confidence coefficients;

[0037] a backup capacity configuration module, configured to configure the backup capacity of each wind power quality layer by using the risk degrees, and to obtain the total backup capacity required for the similar days.

[0038] In a third aspect, the present application further provides a computer device comprising a processor and a memory, the processor being connected with the memory, the memory being used for storing a computer program, and the processor being used for executing the computer program stored in the memory, so that the computer device executes the steps of the above method.

[0039] In a fourth aspect, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0040] The present application provides a method and system for configuring reserve capacity based on wind power quality, which determines the power generation confidence coefficient of each wind power quality layer by layer by dividing the wind power quality and combining the wind power output of similar days, and then obtains the total reserve capacity required by the wind power generator on similar days, considers the large-scale new energy fluctuation, and guarantees the reliability of the power market operation. Compared with the prior art, the method takes into account the reliability and economy at the same time, guarantees the system reliability, ensures that the power system has sufficient reserve capacity during operation, and makes the power system safe and stable, thereby providing an effective reference for the configuration of the reserve capacity of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is a flowchart of the method for configuring reserve capacity based on wind power quality provided by the embodiment of the present application;

[0042] Figure 2 is a schematic diagram of wind power quality layer division provided by the embodiment of the present application;

[0043] Figure 3 is a schematic diagram of a probability distribution function provided by the embodiment of the present application;

[0044] Figure 4 is a block diagram of the reserve capacity configuration system based on wind power quality provided by the embodiment of the present application;

[0045] Figure 5 is a structural schematic diagram of the computer device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0046] The embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments are given only for the purpose of illustration and cannot be understood as limiting the present application. The accompanying drawings are only for reference and illustration, and do not constitute a limitation on the scope of patent protection of the present application, because many changes can be made to the present application without departing from the spirit and scope thereof.

[0047] REFERENCE Figure 1This invention provides a method for configuring reserve capacity based on the power quality of wind power generation, such as... Figure 1 As shown, the method includes the following steps:

[0048] S1. Based on the output performance of the wind turbine, the wind power generation is divided into several wind power generation quality layers; in this embodiment, the output performance of the wind turbine includes the fluctuation of the wind power generation.

[0049] Specifically, this embodiment takes into account the volatility of wind power generation and uses the reliability of wind power generation as the quality evaluation standard, dividing wind power generation into several quality layers. The larger the number of layers, the more refined the division. For ease of description, as follows: Figure 2 As shown, this embodiment uses three wind power generation quality layers as an example for illustration.

[0050] exist Figure 2 In the classification of wind power generation power quality layers, the first layer indicates that the power generation is basically stable, meaning that the power generation can generally reach this level and the power generation in this layer is reliable. The second layer indicates that the power generation fluctuates relatively little, meaning that the daily power generation is likely to fluctuate within this range and is relatively reliable. The third layer indicates that the power generation fluctuates relatively much, meaning that wind power generation can rarely reach this range and is less reliable.

[0051] S2. Perform cluster analysis on the acquired historical meteorological factors and historical wind power generation data to determine similar days.

[0052] In one embodiment, the step of performing cluster analysis on the acquired historical meteorological factors and historical wind power generation data to determine similar days includes:

[0053] The acquired historical meteorological factors and historical wind power generation data are linearly normalized to obtain normalized meteorological factors and normalized wind power generation data. In this embodiment, the historical meteorological factors include historical temperature factors, historical wind speed factors, and historical humidity factors, wherein the formula for linear normalization is:

[0054]

[0055] In the formula, x represents the normalized meteorological factor or normalized wind power generation data; r represents the historical meteorological factor or historical wind power generation data; min(r) represents the minimum value of the historical meteorological factor or historical wind power generation data in the past year; max(r) represents the maximum value of the historical meteorological factor or historical wind power generation data in the past year.

[0056] According to the normalized meteorological factors and the normalized wind power generation data, a similarity index and a discrimination index are calculated; in this embodiment, the calculation formula of the similarity index is:

[0057]

[0058] In the formula, S represents the similarity index; m represents the sample dimension; n represents the total number of historical dates; x ij represents the i-th day, the j-th sample attribute, and the sample attribute includes the normalized meteorological factor or the normalized wind power generation data; represents the average value of the j-th sample attribute;

[0059] The calculation formula of the discrimination index is:

[0060]

[0061] In the formula, D represents the discrimination index; p represents the total number of date categories; P represents the date category number; x iP represents the average value of the P-th category, the j-th sample attribute;

[0062] Based on the similarity index and the discrimination index, a clustering algorithm is used to cluster and divide the normalized meteorological factors and the normalized wind power generation data, to determine similar days.

[0063] It should be noted that, in this embodiment, based on the similarity index and the discrimination index, a clustering algorithm is used to divide the normalized meteorological factors and the normalized wind power generation data into similar days, and when S std and D std , the clustering algorithm meets a preset standard value, wherein S std is an intra-class similarity standard value, and D std is an inter-class discrimination standard value.

[0064] S3. According to the historical wind power generation data of the similar days, determine the power generation confidence coefficients of each wind power generation quality layer.

[0065] In this embodiment, the step of determining the power generation confidence coefficients of each wind power generation quality layer according to the historical wind power generation data of the similar days includes:

[0066] According to the historical wind power generation data of each preset time period of the similar days, determine the probability distribution function of the wind power generation in the power interval;

[0067] According to the probability distribution function, determine the power generation confidence coefficients of each wind power generation quality layer.

[0068] For example, Figure 3As shown, the embodiment determines the probability distribution function of wind power output in the power interval according to the historical wind power generation period data of similar days, and determines the power generation confidence coefficient of each wind power quality layer, and in Figure 3 , Pa(Pw≥P1) = 1, Pa(Pw≥P2) = α, wherein P1, P2, P3 respectively represent the upper limit of unit output of different wind power quality layers, and α represents the probability value corresponding to the maximum output of each wind power quality layer.

[0069] In the embodiment, the probability density of the first layer wind power quality layer is 1, so that P1 can be determined as the minimum power of wind power generation in the similar day, and α is determined according to the demand of wind power quality and reliability demand of the current region.

[0070] S4. Determine the risk degree of each wind power quality layer according to the power generation confidence coefficient.

[0071] The embodiment determines the possibility of wind power generation of each wind power quality layer according to the confidence coefficient obtained in step S3, and defines it as the risk degree β k :β k = 1-α k , wherein α k represents the probability value corresponding to the maximum output of the kth layer wind power quality layer. Figure 3 It can be known that the wind power generation power in the first layer wind power quality layer can be guaranteed to be generated, so that the power can be used as the output of the traditional unit, and the risk degree can be considered as 0; the wind power generation power in the second layer wind power quality layer has a great probability to be generated, but has a risk of being unable to be generated to a certain extent under special circumstances, and the risk degree of the corresponding interval power unable to be generated is 1-α k ; the risk degree of the wind power generation in the third layer wind power quality layer is α, and the risk of the interval power unable to be generated is greater.

[0072] S5. Configure the standby capacity of each wind power quality layer by using the risk degree, and obtain the total standby capacity required to be configured in the similar day.

[0073] In one embodiment, the standby capacity calculation formula of each wind power quality layer is:

[0074] P′ k = (P k -P k-1 )*β k

[0075] In the formula, P′ k represents the standby capacity of the kth layer wind power quality layer; P k represents the upper limit of unit output of the kth layer wind power quality layer; Pk-1 represents the upper limit of the unit output of the k-1th wind power quality layer; β k represents the risk degree of the kth wind power quality layer being unable to generate power.

[0076] In one embodiment, the total backup capacity required for the similar day is obtained, specifically:

[0077]

[0078] In the formula, P total represents the total backup capacity required for the similar day; P' k represents the backup capacity of the kth wind power quality layer; K represents the total number of wind power quality layers.

[0079] Specifically, the risk degree of the wind power generation power of the first wind power quality layer is 0, and no backup capacity is required:

[0080] P'1=0

[0081] wherein P'1represents the backup capacity of the first wind power quality layer;

[0082] The risk degree of the wind power generation power of the second wind power quality layer is β2=1-α2, and the wind power generation power backup capacity P'2of the second wind power quality layer can be:

[0083] P'2=(P2-P1)*β2

[0084] The risk degree of the wind power generation power of the third wind power quality layer is generally large, and the wind power generation power backup capacity P'3of the third wind power quality layer is also large, which can be set as:

[0085] P'3=(P3-P2)*β3

[0086] The backup capacities of the three wind power quality layers are added to obtain the total backup capacity P required for the wind power generator set on the similar day total :

[0087] P total =P'1+P'2+P'3

[0088] The embodiment of the present application provides a reserve capacity configuration method based on wind power quality, wherein the method divides wind power output into quality layers, determines the risk degree of each quality layer according to a probability distribution function of a power interval of wind power processing, determines the reserve capacity of each quality layer according to the risk degree, and determines the total reserve capacity required by a similar day wind power unit, thereby solving the problem of insufficient reserve caused by large-scale new energy fluctuation and load shedding, ensuring sufficient reserve capacity of the power system during operation, improving operation reliability, and enabling the power system to operate safely and stably, thereby providing an effective reference value for power market planning and operation.

[0089] It should be noted that the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0090] In one embodiment, as shown in FIG. 1, the embodiment of the present application provides a reserve capacity configuration system based on wind power quality, and the system comprises: Figure 4 A quality division module 101 is configured to divide wind power quality into several wind power quality layers according to the output performance of a wind power unit.

[0091] A clustering analysis module 102 is configured to perform clustering analysis on the acquired historical meteorological factors and historical wind power data to determine a similar day.

[0092] A confidence coefficient determination module 103 is configured to determine the power generation confidence coefficient of each wind power quality layer according to the historical wind power data of the similar day.

[0093] A risk degree determination module 104 is configured to determine the risk degree of each wind power quality layer that cannot output according to the power generation confidence coefficient.

[0094] A reserve capacity configuration module 105 is configured to configure the reserve capacity of each wind power quality layer by using the risk degree, and acquire the total reserve capacity required by the similar day.

[0095]

[0096] ​The specific limitation of the system for configuring backup capacity based on wind power quality can refer to the limitation of the method for configuring backup capacity based on wind power quality, which will not be repeated here. Those skilled in the art can realize that various modules and steps described in combination with the embodiments disclosed in the present application can be realized in hardware, software or combination of both. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to realize the described functions, but such implementation should not be considered beyond the scope of the present application.

[0097] The embodiment of the present application provides a system for configuring backup capacity based on wind power quality. The system divides the quality of wind power into layers, determines the power generation confidence level of each quality layer in combination with the wind power output of similar days, and further obtains the total backup capacity required by the wind turbine generator of the similar day. Compared with the prior art, the present application does not consider the new energy fluctuation problem in the current backup configuration mode. The capacity requirement to be configured is determined by dividing the quality layer, so as to ensure the safe, reliable and efficient operation of the power system, reduce the risk of instability of the power system, and provide the required wind power backup capacity.

[0098] Figure 5 The embodiment of the present application provides a computer device, which comprises a memory, a processor and a transceiver connected through a bus; the memory is used for storing a set of computer program instructions and data, and can transmit the stored data to the processor; the processor can execute the program instructions stored in the memory to execute the steps of the above method.

[0099] The memory can include volatile memory or non-volatile memory, or can include both volatile and non-volatile memory; the processor can be a central processing unit, a microprocessor, a specific application integrated circuit, a programmable logic device or a combination thereof. By way of example but not limitation, the above programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a general array logic or any combination thereof.

[0100] In addition, the memory can be a physically independent unit, or can be integrated with the processor.

[0101] Those skilled in the art can understand that the structure shown in the above Figure 5 The structure shown in the above

[0102] In one embodiment, the computer readable storage medium having stored thereon computer program is provided, and the computer program is executed by a processor to implement the steps of the above method.

[0103] The method and system for configuring reserve capacity based on wind power quality provided by the embodiments of the present application consider the fluctuation of wind turbine output, and the method for configuring reserve capacity based on wind power quality adopts a quality-based hierarchical method to calculate the reserve capacity configuration, so as to determine reasonable system reserve capacity, ensure sufficient reserve capacity of the power system during operation, improve the safety and stability of the power system operation, and have good application prospect.

[0104] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wire (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.). The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as SSD) and the like.

[0105] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed, the processes of the above-mentioned embodiments can be included.

[0106] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the technical principles of this invention, and these improvements and substitutions should also be considered within the scope of protection of this application. Therefore, the scope of protection of this patent application should be determined by the scope of the claims.

Claims

1. A method for configuring reserve capacity based on wind power generation power quality, characterized in that, Includes the following steps: Based on the output performance of wind turbine units, wind power generation is divided into several quality layers according to its volatility; the number of layers represents different degrees of volatility. Cluster analysis was performed on the acquired historical meteorological factors and historical wind power generation data to identify similar days; Based on historical wind power generation data of similar days, the probability distribution function of each wind power generation power quality layer in the power range is determined, and the power generation confidence coefficient of each wind power generation power quality layer is calculated based on the probability distribution function. Based on the aforementioned power generation confidence coefficient, using formula β k =1-α k Determine the risk level of each wind power generation quality layer failing to generate power; among which, β k The risk level of the k-th layer of wind power generation quality layer being unable to generate power; α k This is the confidence coefficient for power generation; Using the aforementioned risk level, according to formula P k ′=(P k -P k-1 )*β k The standby capacity of each wind power generation power quality layer is configured in a tiered manner; where P k ′ represents the reserve capacity of the k-th wind power generation quality layer; P k P represents the upper limit of the unit output of the k-th wind power generation quality layer; k-1 This represents the upper limit of the unit output of the (k-1)th layer of wind power generation quality layer; Through formula By summing the reserve capacity of each wind power generation quality layer, the total reserve capacity required for the similar days is obtained; where P total This represents the total reserve capacity required for similar days; K represents the total number of wind power generation quality layers.

2. The method for configuring reserve capacity based on wind power generation power quality as described in claim 1, characterized in that, The step of performing cluster analysis on the acquired historical meteorological factors and historical wind power generation data to determine similar days includes: The acquired historical meteorological factors and historical wind power generation data are linearly normalized to obtain normalized meteorological factors and normalized wind power generation data; the historical meteorological factors include historical temperature factors, historical wind speed factors, and historical humidity factors. Based on normalized meteorological factors and normalized wind power generation data, similarity index and discrimination index were calculated. Based on similarity and discriminative indices, clustering algorithms were used to cluster normalized meteorological factors and normalized wind power generation data to determine similar days.

3. The method for configuring reserve capacity based on wind power generation power quality as described in claim 2, characterized in that, The formula for calculating the similarity index is: In the formula, S represents the similarity index; m represents the sample dimension; n represents the total number of historical dates; x ij This represents the attribute of the i-th day and the j-th sample, where the sample attributes include normalized meteorological factors or normalized wind power generation data; This represents the average value of the attribute of the j-th sample; The formula for calculating the discrimination index is as follows: In the formula, D represents the discrimination index; p represents the total number of date categories; P represents the date category number; x iP Let be the average value of the attribute of the j-th sample in class P.

4. The method for configuring reserve capacity based on wind power generation power quality as described in claim 1, characterized in that: The output performance of the wind turbine includes the fluctuation of wind power generation.

5. A standby capacity configuration system based on wind power generation power quality, characterized in that, The system, employing the standby capacity configuration method based on wind power generation quality as described in any one of claims 1 to 4, comprises: The quality classification module is used to classify wind power generation into several quality layers based on the output performance of the wind turbine. The clustering analysis module is used to perform clustering analysis on the acquired historical meteorological factors and historical wind power generation data to determine similar days; The confidence coefficient determination module is used to determine the power generation confidence coefficient of each wind power generation quality layer based on historical wind power generation data of similar days. The risk determination module is used to determine the risk level of each wind power generation power quality layer being unable to generate power based on the power generation confidence coefficient. The standby capacity configuration module is used to configure the standby capacity of each wind power generation power quality layer based on the risk level, and to obtain the total standby capacity required for the similar days.

6. A computer device, characterized in that: The device includes a processor and a memory, the processor being connected to the memory for storing computer programs, and the processor for executing the computer programs stored in the memory to cause the computer device to perform the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 4.

Images